Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely non-obvious behavior: lookups "always return actions and triggers," each carries an AI guidance hint, and with forIntent "only the ones matching your intent carry their full description" while the rest are still listed. That asymmetry would be hard to infer from structured fields alone.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences, purpose front-loaded, then the three modes in priority order. The one flaw is redundancy: "so you pick the right action in one shot" is repeated verbatim in both the tool description and the forIntent schema field.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With eight parameters, 50% schema coverage, and no output schema, the description does the important work of characterizing the return payload (actions, triggers, AI guidance hints, recommendedActions) and mode selection. Gaps remain around default behavior with no arguments, locale semantics, and suggestionType filtering.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 50%, and the description meaningfully expands only two of the eight parameters (pieceNames, forIntent), mostly restating the schema's own examples. It does indirectly clarify why includeActions/includeTriggers are "searchQuery mode" only by contrasting the lookup modes, but locale, categories, and suggestionType remain unexplained in both places.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Research available pieces") and immediately breaks the tool into three distinct modes: pieceNames, searchQuery, and forIntent. An agent can tell what it retrieves. It does not, however, distinguish itself from the closely related siblings ap_search_actions, ap_search_triggers, or ap_get_piece_props, which an agent would need in order to choose correctly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly assigns modes to situations: "Use pieceNames for bulk exact lookup" vs "Use searchQuery for fuzzy discovery" vs "Pass forIntent ... so you pick the right action in one shot." That is real when-to-use guidance. It stops short of exclusions or naming the overlapping sibling tools (ap_search_actions/ap_search_triggers), which is the most likely routing ambiguity here.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.